Evaluation of Deep Learning Methods in a Dual Prediction Scheme to Reduce Transmission Data in a WSN.

One of the most important challenges in Wireless Sensor Networks (WSN) is the extension of the sensors lifetime, which are battery-powered devices, through a reduction in energy consumption. Using data prediction to decrease the amount of transmitted data is one of the approaches to solve this problem. This paper provides a comparison of deep learning methods in a dual prediction scheme to reduce transmission. The structures of the models are presented along with their parameters. A comparison of the models is provided using different performance metrics, together with the percent of points transmitted per threshold, and the errors between the final data received by Base Station (BS) and the measured values. The results show that the model with better performance in the dataset was the model with Attention, saving a considerable amount of data in transmission and still maintaining a good representation of the measured data.

Exploiting the RSSI Long-Term Data of a WSN for the RF Channel Modeling in EPS Environments.

In this paper, we propose a methodology to use the received signal strength indicator (RSSI) available by the protocol stack of an installed Wireless Sensor Network (WSN) at an electric-power-system environment (EPS) as a tool for obtaining the characteristic of its communication channel. Thereby, it is possible to optimize the settings and configuration of the network after its deployment, which is usually run empirically without any previous knowledge of the channel. A study case of a hydroelectric power plant is presented, where measurements recorded over a two-month period were analyzed and treated to obtain the large-scale characteristics of the radiofrequency channel at 2.4 GHz. In addition, we showed that instantaneous RSSI data can also be used to detect specific issues in the network, such as repetitive patterns in the transmitted power level of the nodes, and information about its environment, such as the presence of external sources of electromagnetic interference. As a result, we demonstrate the practical use of the RSSI long-term data generated by the WSN for its own performance optimization and the detection of particular events in an EPS or any similar industrial environment.